Pay Only for Disagreement: Certified No-Regression Verdicts for Model Updates with Matching Label-Complexity Bounds
arXiv 2609.17560v1•fa6cc2b965b2317f5be54e238d8b09776ea3d192f9c2caf6d8cae9d305f9ee1f
Paper metadata
- arXiv ID
- 2609.17560
- Version
- v1
- Category
- cs.AI, cs.CV, cs.LG, stat.ML
- Authors
- Vishnu Bindu Balachandran
- Publication date
- 2026-09-17T04:00:00Z
- Source identifier
- 2609.17560v1
- Public record ID
- record:sha256:fa6cc2b965b2317f5be54e238d8b09776ea3d192f9c2caf6d8cae9d305f9ee1f
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- arxiv_research
- Record identifier
- fa6cc2b965b2317f5be54e238d8b09776ea3d192f9c2caf6d8cae9d305f9ee1f
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.